More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

• URL: http://arxiv.org/abs/2505.21523v3
• Date: Fri, 20 Jun 2025 08:41:41 GMT
• Title: More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
• Authors: Chengzhi Liu, Zhongxing Xu, Qingyue Wei, Juncheng Wu, James Zou, Xin Eric Wang, Yuyin Zhou, Sheng Liu,
• Abstract summary: Test-time compute has empowered large language models to generate extended reasoning chains.<n>As generations become longer, models tend to drift away from image-grounded content and rely more heavily on language priors.
• Score: 43.465268635499754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, this improved reasoning ability often comes with increased hallucination: as generations become longer, models tend to drift away from image-grounded content and rely more heavily on language priors. Attention analysis shows that longer reasoning chains lead to reduced focus on visual inputs, which contributes to hallucination. To systematically study this phenomenon, we introduce RH-AUC, a metric that quantifies how a model's perception accuracy changes with reasoning length, allowing us to evaluate whether the model preserves visual grounding during reasoning. We also release RH-Bench, a diagnostic benchmark that spans a variety of multimodal tasks, designed to assess the trade-off between reasoning ability and hallucination. Our analysis reveals that (i) larger models typically achieve a better balance between reasoning and perception, and (ii) this balance is influenced more by the types and domains of training data than by its overall volume. These findings underscore the importance of evaluation frameworks that jointly consider both reasoning quality and perceptual fidelity.

Related papers

• GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking [35.14983424309319]
  We present GThinker, a novel reasoning MLLM excelling in multimodal reasoning across general scenarios, mathematics, and science.<n>GThinker introduces Cue-Rethinking, a flexible reasoning pattern that grounds inferences in visual cues and iteratively reinterprets these cues to resolve inconsistencies.<n>To support the training, we construct GThinker-11K, comprising 7K high-quality, iteratively-annotated reasoning paths and 4K curated reinforcement learning samples.
  arXiv  Detail & Related papers  (2025-06-01T16:28:26Z)
• The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models [63.98194996746229]
  Large language models (LLMs) have significantly advanced in reasoning tasks through reinforcement learning (RL) optimization.<n>However, reasoning-oriented RL fine-tuning significantly increases the prevalence of hallucinations.<n>We propose Factuality-aware Step-wise Policy Optimization (FSPO), an innovative RL fine-tuning algorithm incorporating explicit factuality verification.
  arXiv  Detail & Related papers  (2025-05-30T14:23:32Z)
• A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models [53.18562650350898]
  Chain-of-thought (CoT) reasoning enhances performance of large language models.<n>We present the first comprehensive study of CoT faithfulness in large vision-language models.
  arXiv  Detail & Related papers  (2025-05-29T18:55:05Z)
• The Mirage of Multimodality: Where Truth is Tested and Honesty Unravels [22.497467057872377]
  This study is the first systematic investigation of distortions associated with System I and System II reasoning in multimodal contexts.<n>We demonstrate that slower reasoning models, when presented with incomplete or misleading visual inputs, are more likely to fabricate plausible yet false details to support flawed reasoning.
  arXiv  Detail & Related papers  (2025-05-26T16:55:38Z)
• Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective [11.013059864022667]
  Reasoning Hallucinations are logically coherent but factually incorrect reasoning traces.<n>These errors are embedded within structured reasoning, making them more difficult to detect and potentially more harmful.<n>We propose the Reasoning Score, which quantifies the depth of reasoning by measuring the divergence between logits.<n>We also introduce GRPO-R, an enhanced reinforcement learning algorithm that incorporates step-level deep reasoning rewards via potential-based shaping.
  arXiv  Detail & Related papers  (2025-05-19T09:16:40Z)
• Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning [12.559028963968247]
  We investigate the crucial relationship between a model's reasoning ability and fairness.<n>We find that larger models with stronger reasoning abilities exhibit substantially lower stereotypical bias.<n>We introduce ReGiFT, a novel approach that extracts structured reasoning traces from advanced reasoning models and infuses them into models that lack such capabilities.
  arXiv  Detail & Related papers  (2025-04-08T03:21:51Z)
• Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy [53.07517728420411]
  We introduce the first instruction database specifically focused on hallucinations in low-level vision tasks.<n>We propose the Self-Awareness Failure Elimination (SAFEQA) model to improve the perception and comprehension abilities of the model in low-level vision tasks.<n>We conduct comprehensive experiments on low-level vision tasks, with the results demonstrating that our proposed method significantly enhances self-awareness of the model in these tasks and reduces hallucinations.
  arXiv  Detail & Related papers  (2025-03-26T16:05:01Z)
• VERIFY: A Benchmark of Visual Explanation and Reasoning for Investigating Multimodal Reasoning Fidelity [34.29409506366145]
  VERIFY is a benchmark designed to isolate and rigorously evaluate the visual reasoning capabilities of state-of-the-art MLLMs.<n>Each problem is accompanied by a human-annotated reasoning path, making it the first to provide in-depth evaluation of model decision-making processes.<n>We propose novel metrics that assess visual reasoning fidelity beyond mere accuracy, highlighting critical imbalances in current model reasoning patterns.
  arXiv  Detail & Related papers  (2025-03-14T16:26:11Z)
• VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models [57.43276586087863]
  Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs. Existing benchmarks are often limited in scope, focusing mainly on object hallucinations. We introduce a multi-dimensional benchmark covering objects, attributes, and relations, with challenging images selected based on associative biases.
  arXiv  Detail & Related papers  (2024-04-22T04:49:22Z)
• Quantity Matters: Towards Assessing and Mitigating Number Hallucination in Large Vision-Language Models [57.42800112251644]
  We focus on a specific type of hallucination-number hallucination, referring to models incorrectly identifying the number of certain objects in pictures. We devise a training approach aimed at improving consistency to reduce number hallucinations, which leads to an 8% enhancement in performance over direct finetuning methods.
  arXiv  Detail & Related papers  (2024-03-03T02:31:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.